[GitHub] [kafka] divijvaidya commented on a diff in pull request #13135: KAFKA-14633: Reduce data copy & buffer allocation during decompression

["divijvaidya (via GitHub)" <gi...@apache.org>]

divijvaidya commented on code in PR #13135:
URL: https://github.com/apache/kafka/pull/13135#discussion_r1200351208


##########
clients/src/main/java/org/apache/kafka/common/utils/ChunkedBytesStream.java:
##########
@@ -0,0 +1,357 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.kafka.common.utils;
+
+import java.io.BufferedInputStream;
+import java.io.FilterInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.ByteBuffer;
+
+/**
+ * ChunkedBytesStream is a copy of {@link ByteBufferInputStream} with the following differences:
+ * - Unlike {@link java.io.BufferedInputStream#skip(long)} this class could be configured to not push skip() to
+ * input stream. We may want to avoid pushing this to input stream because it's implementation maybe inefficient,
+ * e.g. the case of ZstdInputStream which allocates a new buffer from buffer pool, per skip call.
+ * - Unlike {@link java.io.BufferedInputStream}, which allocates an intermediate buffer, this uses a buffer supplier to
+ * create the intermediate buffer.
+ * <p>
+ * Note that:
+ * - this class is not thread safe and shouldn't be used in scenarios where multiple threads access this.
+ * - the implementation of this class is performance sensitive. Minor changes such as usage of ByteBuffer instead of byte[]
+ * can significantly impact performance, hence, proceed with caution.
+ */
+public class ChunkedBytesStream extends FilterInputStream {
+    /**
+     * Supplies the ByteBuffer which is used as intermediate buffer to store the chunk of output data.
+     */
+    private final BufferSupplier bufferSupplier;
+    /**
+     * Intermediate buffer to store the chunk of output data. The ChunkedBytesStream is considered closed if
+     * this buffer is null.
+     */
+    private byte[] intermediateBuf;
+    /**
+     * The index one greater than the index of the last valid byte in
+     * the buffer.
+     * This value is always in the range <code>0</code> through <code>intermediateBuf.length</code>;
+     * elements <code>intermediateBuf[0]</code>  through <code>intermediateBuf[count-1]
+     * </code>contain buffered input data obtained
+     * from the underlying  input stream.
+     */
+    protected int count = 0;
+    /**
+     * The current position in the buffer. This is the index of the next
+     * character to be read from the <code>buf</code> array.
+     * <p>
+     * This value is always in the range <code>0</code>
+     * through <code>count</code>. If it is less
+     * than <code>count</code>, then  <code>intermediateBuf[pos]</code>
+     * is the next byte to be supplied as input;
+     * if it is equal to <code>count</code>, then
+     * the  next <code>read</code> or <code>skip</code>
+     * operation will require more bytes to be
+     * read from the contained  input stream.
+     */
+    protected int pos = 0;
+    /**
+     * Reference for the intermediate buffer. This reference is only kept for releasing the buffer from the
+     * buffer supplier.
+     */
+    private final ByteBuffer intermediateBufRef;
+    /**
+     * Determines if the skip be pushed down
+     */
+    private final boolean pushSkipToSourceStream;
+
+    public ChunkedBytesStream(InputStream in, BufferSupplier bufferSupplier, int intermediateBufSize, boolean pushSkipToSourceStream) {
+        super(in);
+        this.bufferSupplier = bufferSupplier;
+        intermediateBufRef = bufferSupplier.get(intermediateBufSize);
+        if (!intermediateBufRef.hasArray() || (intermediateBufRef.arrayOffset() != 0)) {
+            throw new IllegalArgumentException("provided ByteBuffer lacks array or has non-zero arrayOffset");
+        }
+        intermediateBuf = intermediateBufRef.array();
+        this.pushSkipToSourceStream = pushSkipToSourceStream;
+    }
+
+    /**
+     * Check to make sure that buffer has not been nulled out due to
+     * close; if not return it;
+     */
+    private byte[] getBufIfOpen() throws IOException {
+        byte[] buffer = intermediateBuf;
+        if (buffer == null)
+            throw new IOException("Stream closed");
+        return buffer;
+    }
+
+    /**
+     * See

Review Comment:
   Indentation problem. Fixed it.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: jira-unsubscribe@kafka.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org